use LWP::UserAgent;
use HTTP::Request;
use HTTP::Response;
use Spreadsheet::WriteExcel;
use FileHandle;

use strict;

# create useragent, open an excel workbook and sheet

my $ua = LWP::UserAgent -> new;
my $workbook = Spreadsheet::WriteExcel -> new ( "IPA.xls" );
my $sheet = $workbook -> add_worksheet ( );
$sheet -> set_column ( 0, 0, 100 );

# get html source and parse

my $address = "http://dictionary.reference.com/browse/hello";
my $request = HTTP::Request -> new ( GET => $address );
my $response = $ua -> request ( $request );
my $htmlsource;
my $writestring;

if ( $response -> is_success ) {
	$htmlsource = $response -> content;
	$writestring = parse( $htmlsource );
}

# write to spreadsheet, close excel

$sheet -> write ( 0, 0, $writestring );
$workbook -> close ( );

sub parse {
	my $source = shift;
	my $htmlchunk;
	my $ipa;

	# select from html source the chunk of html which contains IPA-
	# encoded symbols
	# this chunk will still contain html tags that need to be removed
	# i'll find it between the *first* (but perhaps not last) pairing 
	# of these two surrounding strings:
	#    "prondelim">/</span><span class="pron"
	#    /span><span class="prondelim"
	
	if ( $source =~ /"prondelim">\/<\/span><span class="pron"(.*?)\/span><span class="prondelim"/ ) {
		$htmlchunk = $1;
	}

	# get rid of leading html tags, save the IPA or English bits 
	# between '>' and '<',
	# and continue doing the same over the remaining chunk

	while ( $htmlchunk =~ /(.*?)>(.*?)<(.*)/ ) {
		$ipa = $ipa . $2;
		$htmlchunk = $3;
	}
	
	return $ipa;
}